Brainscape's Knowledge GenomeTM

Browse over 1 million classes created by top students, professors, publishers, and experts.


See full index

SPA 720 > Test 2 > Flashcards

Test 2 Flashcards

1
Q

Systematic Review

A

A systematic way of identifying studies with similar outcome measures. No statistics are present. Collect and critically analyzes multiple research studies.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

Meta-analysis

A

particular procedure to identify trends in the statistical results of a set of studies concerning the same research problem. Identifies studies with a particular outcome measure. Conducts statistics and develops a single conclusion.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

Level of Evidence

A
  1. systematic reviews
  2. critically appraised synopsis/synthesis
  3. randomized controlled trials
  4. cohort/case-controlled studies, guidelines
  5. case reports/series
  6. review articles
  7. background information: textbooks
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

Correlation

A

Don’t manipulate IV, observe who gets IV and how much of it and then see how it influences DV. Could have comparison groups.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

Descriptive

A

The goal is to describe a phenomenon, with no manipulation of variables, does not demonstrate cause-effect, can be prospective/retrospective, the classification variable is analogous to IV, criterion variable is analogous to DV. Nonexperimental, survey, comparative, developmental and correlational.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

Single Subject Study

A

experimental/nonexperimental, manipulates IV, no group to decide who gets independent variable involves 1-6 subjects, use individual as a control, helps establish cause-effect relations based on individual performance as opposed to group averages.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

Case Studies

A

can/cannot manipulate IV. No comparison/control groups. assessment is not systematic.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
8
Q

prospective

A

the investigator states 1 or more hypotheses, identifies the kinds of participants and procedures needed to test the hypothesis, recruits participants, and begins collecting data.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

Retrospective

A

the investigator analyzes data that already existed prior to the investigation so they have no control over the participants from who or the means by which the data were collected. Ranked lower than prospective designs.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

Experimental

A

uses the scientific method to establish a cause-effect relationship among a group of variables that make up a study. manipulation of IV, control, and randomization. 2 or more groups. Prospective.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

Nonexperimental

A

the investigator’s intent is not to alter a situation but rather to observe in a systematic fashion. 1 group. Is observed.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
12
Q

Controlled (comparison)

A

the study has been designed to compare results from different participants or different conditions. 2/more groups, use of control groups, experimental groups.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
13
Q

Uncontrolled (non-comparison)

A

simple report on the characteristics of a single individual, group, or condition. No comparison, 1 group, observational, case study.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

Randomized

A

Randomly draw a small group from the population. Each potential participant in the population has an equal chance of being selected for the study.
Use randomization or matching.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
15
Q

Not randomized

A
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
16
Q

Independent variable

A

what is directly manipulated by experimenter?

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
17
Q

Dependent variable (outcome measure)

A

the variable that is affected by the manipulation of an independent variable. they are measurable.

18
Q

Null hypothesis

A

hypothesis that there is no significant difference between specified populations, any observed difference being due to sampling/experimental error. means zero, the 2 variables are not related H_0.

19
Q

Research hypothesis

A

a definite statement that there is a relationship between variables, H_a.

20
Q

Statements of Central Tendency

A

Average
mean = scores are summed and divided by the number of observations (most common type).
median = 50% of cases in a distribution fall below and 50% fall below (midpoint) even numbers then add the two and find the mean.
mode = most frequently occurring score in a distribution/no formula.
the mean of group name (#) was higher than group name (#) at the post-test.

21
Q

Statement of variance

A

range = highest minus lowest score and gross measure of variability (most general measure) how far apart score from one another.
standard deviation = average deviation from mean; used most frequently; average distance from the mean; subtract mean from each score then square each individual difference sum all squared deviations about mean divide sum by n-1 compute the square root.
variance = square standard deviation and another measure of distribution’s spread/dispersion, so you skip the last step.
range of group name (#) is larger than group name (#).

22
Q

Type I Error

A

The null hypothesis is true but rejected. False positive.

23
Q

Type II Error

A

Null is false but it is accepted. The Null is false.

24
Q

Significance Level (apriori) Alpha

A

level of significance that is selected prior to data collection for accepting or rejecting the null hypothesis is alpha. the probability of making a Type I Error, the degree of risk of a false positive.

25
Q

p-value probability value

A

level of significance actually obtained after data has been collected and analyzed.

26
Q

Statistical significance (t-test)

A

the determination that a relationship between 2 or more variables is caused by something other than chance. The resulting p-value is less than the pre-defined alpha level.

27
Q

p-value is .05

A

95% probability the observed effect was NOT due to chance.
5% probability the observed effect was due to chance.

28
Q

Interpret correlation matrix

A

there is a statistical significance direction strength relationship between variable 1 and variable 2.

29
Q

correlational coefficient

A

the numerical index that reflects the relationship between 2 variables. The ranges -1.0 and +1.0.

30
Q

Direct (+) correlation

A

variables change in the same direction.
both variables go up/go down.

31
Q

indirect (-) correlation

A

variables change in opposite directions.
1 variable increases, other decreases.

32
Q

Calculate Cohen’s d

A

(Mean 1 – Mean 2)
Averaged SD

33
Q

interpret Cohen’s d

A

0.2 = small
0.5 = medium
0.8 = large
comparison of mean scores.

34
Q

interpret eta squared

A

eta squared times 100% of the variability in the data is accounted for by the difference between treatments.
the sum of squares between groups divided by total SS.
.01 = small
.06 = medium
.14 = large

35
Q

Pearson’s r (correlation/regression)

A

small = .10
medium = .30
large = .50
test for linear relationships between data.

36
Q

R^2 (better for regression)

A

small = .01
medium = .06
large = .14
coefficient of determination - designed to calculate the relationship/correlation between 2/more variables.
can explain both simple and multiple linear regressions.

37
Q

correlation

A

the proportion of variation in DV that can be attributed to IV.
tells us that the number of hours of therapy predicts about 25% of the variation in articulation test scores and conversely that articulation score accounts for ~25% of the variance in the number of hours of therapy.

38
Q

Regression

A

a value that reflects the percentage of variation in 1 measure (Y or DV) that can be explained/predicted by others (X IV variables).
r^2 is a statistical measure that represents the proportion of variance for DV that is explained by IV or variables in the regression model.

39
Q

X-Axis

A

independent variable

40
Q

Y-Axis

A

dependent variable

41
Q

Strength of Correlation

A

1 = perfect
.7 - .9 = strong
.4 - .6 = moderate
.1 - .3 = weak
0 = zero

42
Q

Prioritize External Evidence

A

meta-analyses
systematic reviews
randomized control studies
quasi-experimental
correlational/descriptive
single subject
case studies

SPA 720 (1 decks)

Brainscape helps you reach your goals faster, through stronger study habits.
© 2024 Bold Learning Solutions. Terms and Conditions